CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

supabase-automation

Automate Supabase database queries, table management, project administration, storage, edge functions, and SQL execution via Rube MCP (Composio). Always search tools first for current schemas.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/supabase-automation/SKILL.md

The canonical home for this skill is supabase-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, highly actionable MCP tool reference with clearly sequenced workflows and genuinely useful pitfalls. Its weaknesses are token-inefficient duplication of pitfalls across sections plus filler sections, and the absence of validation/verification feedback loops around destructive SQL write operations.

Suggestions

Consolidate the duplicated pitfall material: the "Known Pitfalls" section restates array syntax, ID formats, error codes, and service-health pitfalls already covered in the workflow sections — keep one authoritative location and cross-reference it.

Delete the empty "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") and replace tautological parameter descriptions ("`ref`: Project reference") with only non-obvious details.

Add post-write validation steps to the SQL workflow, e.g. verify affected rows or re-query the table after INSERT/UPDATE/DELETE, and a validate-and-retry loop for DDL, so destructive database operations have explicit feedback checkpoints.

DimensionReasoningScore

Conciseness

The body is dense and largely free of concept over-explanation, but wastes tokens on repetition: pitfalls appear in both workflow sections and again in "Known Pitfalls" (array syntax stated three times, ID format three times, service health twice), several parameters are tautological ("`ref`: Project reference"), and the "When to Use" section is filler ("This skill is applicable to execute the workflow or actions described in the overview."). Mostly efficient but needs tightening, matching anchor 3.

3 / 5

Actionability

Concrete, executable guidance throughout: exact tool slugs, ordered sequences with [Prerequisite]/[Required]/[Optional] markers, precise parameter names, PostgREST filter operators, error codes (42P01, 42883), and the project-ref pattern `^[a-z]{20}$`. Minor gap: no example JSON payloads or sample invocations, so it stops just short of fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

Sequences are clearly ordered and setup includes a checkpoint (confirm connection ACTIVE before running workflows), and pre-write schema inspection is advised. However the SQL write workflows (INSERT/UPDATE/DELETE, DDL) include no post-write verification or validate-and-retry feedback loop; the rubric's scoring note caps workflow clarity at 3 for database/destructive operations lacking validation.

3 / 5

Progressive Disclosure

No bundle files exist, and the single file is well-organized with clear sections (Prerequisites, Setup, five numbered workflows, Common Patterns, Known Pitfalls) plus a navigable Quick Reference table. Good structure and easy navigation; the minor gap is that the ~230 lines of per-tool parameter and pitfall detail could be split into a reference file, keeping it at anchor 4 rather than 5.

4 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, well-scoped, and clearly distinct thanks to the Supabase + Rube MCP framing, with good natural trigger terms. Its main weakness is the complete absence of a 'when to use' trigger clause, which caps completeness at 3 and leaves a natural-phrase gap.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Supabase, wants to query or modify a Supabase database, run SQL, manage Supabase projects/organizations, storage buckets, or edge functions."

Include common user phrasings and synonyms in the trigger terms, such as "run SQL", "Postgres queries", or "query my Supabase data", to strengthen trigger_term_quality.

Optionally note the concrete action granularity (e.g. "query tables, run raw SQL, inspect schemas, generate TypeScript types") to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Automate Supabase database queries, table management, project administration, storage, edge functions, and SQL execution" lists several concrete capability areas with action verbs, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the actions are domain-level categories rather than fine-grained operations like 'extract text, fill forms, merge documents'.

4 / 5

Completeness

The 'what' is clear and specific (automating Supabase operations via Rube MCP/Composio), but there is no 'Use when...' clause or equivalent trigger guidance; "Always search tools first for current schemas" is procedural, not a when-trigger. Per the rubric guideline, a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present ("Supabase", "database queries", "SQL", "storage", "edge functions"), giving good keyword coverage. Missing a few natural variations like "run SQL", "query my database", or "Postgres", so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"...via Rube MCP (Composio)" plus the Supabase-specific scope carves out a clear niche with distinct triggers and minimal conflict risk with other skills, matching the anchor-5 example's structure.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/supabase-automation/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.